Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of specific physical locations, particularly road intersections

    oai_token-act-pair · gpt-3.5-turbo

    references to intersections, both literal and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesia
    -0.69
    zin
    -0.69
    wagen
    -0.68
    zel
    -0.68
    sonian
    -0.67
    iken
    -0.67
    warm
    -0.67
     captivity
    -0.67
    apons
    -0.65
    vier
    -0.65
    POSITIVE LOGITS
     Sakuya
    0.82
     intersection
    0.81
     intersections
    0.77
    aminer
    0.75
    cross
    0.74
     between
    0.73
     Beir
    0.73
    points
    0.71
    alis
    0.71
     mund
    0.71
    Act Density 0.043%

    No Known Activations